Update app.py

app.py

@@ -3,6 +3,8 @@ from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from llama_cpp import Llama
 from contextlib import asynccontextmanager
+from huggingface_hub import hf_hub_download
+
 
 # =========================
 # MODEL CONFIG
@@ -10,6 +12,12 @@ from contextlib import asynccontextmanager
 MODEL_REPO = "bartowski/Phi-3.1-mini-4k-instruct-GGUF"
 MODEL_FILE = "Phi-3.1-mini-4k-instruct-IQ2_M.gguf"
 
+MODEL_PATH = hf_hub_download(
+    repo_id=MODEL_REPO,
+    filename=MODEL_FILE,
+)
+
+
 N_THREADS = int(os.getenv("N_THREADS", "8"))
 N_CTX = int(os.getenv("N_CTX", "2048"))
 N_BATCH = int(os.getenv("N_BATCH", "256"))
@@ -23,12 +31,13 @@ llm = None
 async def lifespan(app: FastAPI):
     global llm
     llm = Llama(
-        model_path=MODEL_FILE,
-        n_ctx=N_CTX,
-        n_threads=N_THREADS,
-        n_batch=N_BATCH,
-        verbose=False,
+    model_path=MODEL_PATH,
+    n_ctx=N_CTX,
+    n_threads=N_THREADS,
+    n_batch=N_BATCH,
+    verbose=False,
     )
+
     yield
 
 app = FastAPI(title="AI Humanizer", lifespan=lifespan)